Odel

AI & agents

Memory, payments and tools for AI agents, other agents to work with, and gateways to more tools.

13,023 servers6,999 publishers11 tags

All of AI & agents

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
GrayMatter
@valkyrlabs · External

Secure durable memory and bounded context for AI agents, with hosted OAuth and local Lite support.

15% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
mcp-pin
@gautamtalksdev · External

Check if an MCP server's tool definitions changed after approval, from a signed public log.

3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Nimbus BCI
@nimbusbci · External

AI agents build, train, and analyze BCI/EEG pipelines: data, models, experiments, live sessions.

Not assessed yet.What it can do is not assessed yet.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Ramen: self-hosted MCP for teams
@bkraad47 · External

Multi-zone MCP server for GKE/EKS/AKS: Python tools from git, NeMo guardrails, SSO, autoscaling.

4% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.Free to use.
MCP server: One MCP server.
Google E-commerce (GA4, Search Console, Merchant Center)
@mooneyes · External

Read-only GA4, Search Console, Merchant Center, Tag Manager, Indexing and PageSpeed for shops.

4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Al Buddy MemoryRun by its publisher: served from their own domain, namespace checked by the registry.
@flytomoon · External

Governed local memory for AI agents: facts are retired, not overwritten, and every call is audited.

3% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
RugSnare
@paraphern · External

Pin MCP tool contracts by sha-256; catch silent drift, rug pulls and bait-and-switch in CI.

4% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Win Mind
@jhonpork1233-beep · External

See and drive any Windows app via the accessibility tree - no screenshots - plus 200+ native tools

11% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.Free to use.
MCP server: One MCP server.
PL/SQL Intelligence
@muhdur · External

Oracle MCP with PL/SQL analysis, lineage, SAST, and change-impact tools.

4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Deprecated by the publisher: plsql-mcp is retired; use oraclemcp with the plsql-intelligence feature.Free to use.
MCP server: One MCP server.
MateMCP
@vrassouli · External

Your agent hit a limit? Keep working. MateMCP securely connects AI chats to your computer via MCP.

Not assessed yet.What it can do is not assessed yet.Runs on your machine, installed from a package registry.Free to use.
MCP server: One MCP server.
agent-mailbox — Mailbox and Wake System for AI Agent Teams
@polaris-smart · External

Mailbox + wake system for AI agent teams: letters always land, right agent wakes, quiet otherwise.

Not assessed yet.What it can do is not assessed yet.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
MIMIRRun by its publisher: served from their own domain, namespace checked by the registry.
@abderahmane-ai · External

Typed, calibrated and certified decisions over a context, with abstention and evidence.

3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Thread Mind
@mahmoud-nb · External

Git-friendly memory for AI coding: a tree of thread summaries with inherited context

4% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Diavlos
@harisnopen · External

Signed messages between AI agents. Dangerous actions wait for a human-signed approval.

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.Free to use.
MCP server: One MCP server.
Builderforce MemoryRun by its publisher: served from their own domain, namespace checked by the registry.
@seanhogg · External

Token-saving persistent memory for AI agents: recall durable facts instead of re-reading files.

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
OpenMMRun by its publisher: served from their own domain, namespace checked by the registry.
@qbt-labs · External

MCP server for OpenMM — exposes market data, account, trading, and strategy tools to AI agents

9% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
The Tab (scvd-tab)Run by its publisher: served from their own domain, namespace checked by the registry.
@scvd · External

Every tool a builder signs up for, on one tab: trials, burn, price drift. Local JSONL, zero deps.

7% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Tenzro Canton MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@tenzro-network · External

Canton MCP: DAML submit, contracts, events, parties, domains, CIP-56 tokens, DvP, DAR upload.

7% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 13 Oct.Free to use.
MCP server: One MCP server.
Alpaca Guard
@evidai · External

Alpaca trading API with hard daily USD cap guard. Paper trading default; live opt-in.

11% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Intents
@vladuzh · External

Your Mac's App Intents (Reminders, Calendar, Notes…) as MCP tools via Shortcuts. Public APIs only.

4% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.Free to use.
MCP server: One MCP server.
MCPower Security Proxy
@mcpower-security · External

Security proxy that automatically wraps MCP servers with real-time monitoring and policy enforcement

13% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Ramus AndroidRun by its publisher: served from their own domain, namespace checked by the registry.
@ramus · External

Disposable cloud Android emulators for coding agents: run an APK or PR build, tap, type, screenshot.

8% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
GRAFOMEM CGR ReadRun by its publisher: served from their own domain, namespace checked by the registry.
@grafomem · External

Read Foundation-signed, offline-verifiable CGR agent-reputation attestations. No install.

6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; it needs your API key.Free to use.
MCP server: One MCP server.
CoS Codex Bridge
@av-labs-co · External

Operate Codex projects and tasks from a Chief of Staff with scoped access and durable receipts.

8% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.

More topics

Sales & customersMarketing & advertisingShopping & e-commerceBusiness financePersonal finance & investingLegal & governmentSecurity & privacySoftware developmentCloud & IT operationsData & webWork & productivityCommunicationDocuments & writingDesign & mediaNews & informationScience & researchHealth & fitnessEducation & careersTravel & placesHome & propertyEntertainment & hobbiesIndustry & transport